UTI-to-STFT-Tacotron2

Implementation of Csaba Zainkó, László Tóth, Amin Honarmandi Shandiz, Gábor Gosztolya, Alexandra Markó, Géza Németh, Tamás Gábor Csapó, ,,Adaptation of Tacotron2-based Text-To-Speech for Articulatory-to-Acoustic Mapping using Ultrasound Tongue Imaging'', ISCA 11th Speech Synthesis Workshop (SSW11), 2021, accepted, arXiv:2107.12051

Ultrasound-to-Symbol using 3D-CNN

• code for training
• code for prediction

Requirements

• Python 3.6.9
• keras 2.2.4
• tensorflow-gpu 1.13.1
• pytorch 1.2.0
• ...etc... see requirements.txt